System and method for distinguishing a cardiac event from noise in an electrocardiogram (ECG) signal

Abstract

A cardiac monitoring device includes: at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient; a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to: obtain the ECG signal from the at least one sensing electrode; determine a transformed ECG signal based on the ECG signal; extract at least one value representing at least one feature of the transformed ECG signal; provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score; compare the ECG-derived score to a predetermined threshold score determined by machine learning; and provide an indication of a cardiac event if the ECG-derived score is one of above or below the predetermined threshold score determined by the machine learning.

The invention claimed is: 
     
       1. A wearable defibrillator comprising:
 at least one therapy pad for rendering treatment to a patient wearing the wearable defibrillator; 
 at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from the patient; 
 a processing unit comprising at least one processor operatively coupled to the at least one therapy pad and the at least one sensing electrode; and 
 at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the processing unit to:
 obtain the ECG signal; 
 determine a transformed ECG signal based on the ECG signal; 
 extract at least one value representing at least one feature of the transformed ECG signal; 
 provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score; 
 compare the ECG-derived score to a predetermined threshold score determined by machine learning; and 
 provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score, 
 
 wherein the transformed ECG signal comprises a power spectral density (PSD) of the ECG signal, the PSD being determined by calculating a fast Fourier transform (FFT) of the ECG signal, and 
 wherein at least four features of the PSD are extracted and provided to the machine learning. 
 
     
     
       2. The wearable defibrillator of  claim 1 , wherein the transformed ECG signal comprises a frequency-domain representation of the ECG signal. 
     
     
       3. The wearable defibrillator of  claim 1 , wherein the transformed ECG signal comprises a representation of a power distribution of the ECG signal over a range of frequencies of the ECG signal. 
     
     
       4. The wearable defibrillator of  claim 1 , wherein the at least four features of the PSD that are extracted are: at least one value representing a dominant frequency of the PSD; at least one value representing in-band entropy of the PSD between frequencies of 2 Hz and 6 Hz; at least one value representing first-band entropy of the PSD between frequencies of 0 Hz and 2 Hz; and at least one value representing a variance of the PSD. 
     
     
       5. The wearable defibrillator of  claim 1 , wherein determining the PSD comprises calculating the fast Fourier transform (FFT) of the ECG signal and performing a square of a modulus of the FFT to transform the FFT into a real number. 
     
     
       6. The wearable defibrillator of  claim 1 , wherein the machine learning is one of a multivariate adaptive regression splines classifier and a neural network classifier. 
     
     
       7. The wearable defibrillator of  claim 1 , further comprising at least one response mechanism operatively connected to the at least one processor,
 wherein the wearable defibrillator is configured to prevent rendering treatment to the patient wearing the wearable defibrillator in response to a patient actuation of the at least one response mechanism. 
 
     
     
       8. The wearable defibrillator of  claim 1 , further comprising:
 providing an instruction signal for taking an action based on the indication. 
 
     
     
       9. The wearable defibrillator of  claim 8 , wherein the action is at least one of applying a therapy to a patient and providing a warning signal to the patient. 
     
     
       10. The wearable defibrillator of  claim 8 , further comprising an alert device operatively coupled to the at least one processor for providing the instruction signal to the patient. 
     
     
       11. The wearable defibrillator of  claim 1 , wherein the program instructions that are executed by the at least one processor are initiated for a portion of the ECG signal that is stored in a memory device when the at least one processor detects a triggering event. 
     
     
       12. The wearable defibrillator of  claim 11 , wherein the portion of the ECG signal is a predetermined time period of the ECG signal that precedes the triggering event. 
     
     
       13. The wearable defibrillator of  claim 12 , wherein the predetermined time period is 20 seconds. 
     
     
       14. The wearable defibrillator of  claim 11 , wherein the triggering event is at least one of detection of a ventricular fibrillation (VF) in the ECG signal and detection of a ventricular tachycardia (VT) event in the ECG signal. 
     
     
       15. The wearable defibrillator of  claim 1 , wherein the machine learning is based on a training data set comprising a collection of ECG signals stored in a memory of the wearable defibrillator. 
     
     
       16. The wearable defibrillator of  claim 1 , wherein the indication of the cardiac event is provided if the ECG-derived score is one of above or below the predetermined threshold score. 
     
     
       17. The wearable defibrillator of  claim 1 , wherein the program instructions executed by the at least one processor are performed during a delay period in which an alert device operatively coupled to the at least one processor does not provide a signal to the patient. 
     
     
       18. The wearable defibrillator of  claim 17 , wherein the delay period is one of about 10 seconds and about 30 seconds. 
     
     
       19. A wearable defibrillator comprising:
 at least one therapy pad for rendering treatment to a patient wearing the wearable defibrillator; 
 at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from the patient; 
 a processing unit comprising at least one processor operatively coupled to the at least one therapy pad and the at least one sensing electrode; and 
 at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the processing unit to:
 obtain the ECG signal; 
 determine a transformed ECG signal based on the ECG signal; 
 extract at least one value representing at least one feature of the transformed ECG signal; 
 provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score; 
 compare the ECG-derived score to a predetermined threshold score determined by machine learning; and 
 provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score, 
 
 wherein the machine learning is based on a training data set comprising a collection of ECG signals associated with treatments performed by a plurality of defibrillators. 
 
     
     
       20. The wearable defibrillator of  claim 19 , wherein the collection of ECG signals includes at least noisy normal sinus rhythm signals and tachyarrhythmia signals. 
     
     
       21. A wearable defibrillator comprising:
 at least one therapy pad for rendering treatment to a patient wearing the wearable defibrillator; 
 at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from the patient; 
 a processing unit comprising at least one processor operatively coupled to the at least one therapy pad and the at least one sensing electrode; and 
 at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the processing unit to:
 obtain the ECG signal; 
 determine a transformed ECG signal based on the ECG signal; 
 extract at least one value representing at least one feature of the transformed ECG signal; 
 provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score; 
 compare the ECG-derived score to a predetermined threshold score determined by machine learning; and 
 provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score, 
 
 wherein the machine learning is one of a multivariate adaptive regression splines classifier and a neural network classifier. 
 
     
     
       22. A wearable defibrillator comprising:
 at least one therapy pad for rendering treatment to a patient wearing the wearable defibrillator; 
 at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from the patient; 
 a processing unit comprising at least one processor operatively coupled to the at least one therapy pad and the at least one sensing electrode; and 
 at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the processing unit to:
 obtain the ECG signal; 
 determine a transformed ECG signal based on the ECG signal; 
 extract at least one value representing at least one feature of the transformed ECG signal; 
 provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score; 
 compare the ECG-derived score to a predetermined threshold score determined by machine learning; and 
 provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score, 
 
 wherein the machine learning is based on a training data set comprising a collection of ECG signals stored in a memory of the wearable defibrillator.